Senior On-Device ML Engineer — Real-Time Game AI

Unity Enterprise; San Francisco (CA); Hybrid; USD 218,000 - 284,000; Full time

Benefits offered by this job

Health insurance

Stock options

Retirement plan

Vacation days

Parental leave

Office snacks

Wellbeing programs

Employee Resource Groups

Training & development

Volunteer program

Job summary

Unity is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to optimize and deploy multi-modal models on mobile and constrained hardware. You will own the inference stack from export to kernel-level tuning, shaping latency, memory, and power within a fixed budget.

The role requires hands-on work with WebGPU, native kernels, and major runtimes, plus collaboration across platform, runtime, and game-engine teams. Strong C++/Python and on-device benchmarking are valued.

Qualifications

• 5+ years in software/ML engineering, with meaningful time focused on on-device / edge inference or real-time, performance-critical systems.
• Production deployment of transformer- and/or diffusion-based models on mobile, desktop, or embedded hardware — shipped, not just prototyped.
• Hands-on experience with at least one major inference runtime (ORT Web, CoreML, TFLite, ExecuTorch) and knowledge of operator fusion, memory layout, and runtime scheduling.
• Low-level performance engineering: proficiency with at least one GPU/compute API (WebGPU/WGSL, Metal, Vulkan, D3D12, CUDA) and profiling tools.
• Familiarity with model-optimization techniques — quantization, weight sharing, pruning, and distillation — for latency and memory budgets.

Responsibilities

• Own the optimization pipeline for on-device models: export, graph transforms, fusion, memory layout, and hardware tuning across NPUs and GPUs.
• Write and tune WebGPU compute shaders and native kernels; profile with browser and platform tools; identify bottlenecks at op and memory bandwidth levels.
• Apply efficiency techniques such as dynamic resolution, token reduction, and cross-frame caching to meet budget targets.
• Work with WebGPU inference runtimes and native options; extend glue code where off-the-shelf options fall short of workloads.
• Implement integration between ML runtime and game engine: real-time scheduling, memory pooling, and zero-copy buffers with rendering paths.

Job description

Unity is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to optimize and deploy multi-modal models on mobile and constrained hardware. You will own the inference stack from export to kernel-level tuning, shaping latency, memory, and power within a fixed budget.

The role requires hands-on work with WebGPU, native kernels, and major runtimes, plus collaboration across platform, runtime, and game-engine teams. Strong C++/Python and on-device benchmarking are valued.